paper-with-me

홈 › Papers

Take More Positives: An Empirical Study of Contrastive Learing in Unsupervised Person Re-Identification

2021-01-12 · Xuanyu He, Wei zhang, Ran Song, Qian Zhang, Xiangyuan Lan, Lin Ma

Unsupervised person re-identification (re-ID) aims at closing the performance gap to supervised methods. These methods build reliable relationship between data points while learning representations. However, we empirically show that the reason why they are successful is not only their label generation mechanisms, but also their unexplored designs. By studying two unsupervised person re-ID methods in a cross-method way, we point out a hard negative problem is handled implicitly by their designs of data augmentations and PK sampler respectively. In this paper, we find another simple solution for the problem, i.e., taking more positives during training, by which we generate pseudo-labels and update models in an iterative manner. Based on our findings, we propose a contrastive learning method without a memory back for unsupervised person re-ID. Our method works well on benchmark datasets and outperforms the state-of-the-art methods. Code will be made available.

📄 PDF Abstract BibTeX arXiv:2101.04340

Code (0)

등록된 구현이 없습니다.

Tasks

Contrastive LearningPerson Re-IdentificationUnsupervised Person Re-Identification

Methods 이 논문이 사용한 방법론

Contrastive Learning 설명 없음

Similar Papers 제목 키워드 기반

Learning Sound Localization Better From Semantically Similar Samples

2022-02-07 · Arda Senocak, Hyeonggon Ryu, Junsik Kim, In So Kweon

The objective of this work is to localize the sound sources in visual scenes. Existing audio-visual works employ contrastive learning by assigning corresponding audio-visual pairs from the same source as positives while …

Contrastive Learning

Tuned Contrastive Learning

2023-05-18 · Chaitanya Animesh, Manmohan Chandraker

In recent times, contrastive learning based loss functions have become increasingly popular for visual self-supervised representation learning owing to their state-of-the-art (SOTA) performance. Most of the modern contra…

Contrastive LearningRepresentation LearningSelf-Supervised Learning

With a Little Help from My Friends: Nearest-Neighbor Contrastive Learning of Visual Representations

2021-04-29 · ICCV 2021 10 · Debidatta Dwibedi, Yusuf Aytar, Jonathan Tompson, Pierre Sermanet 외

Self-supervised learning algorithms based on instance discrimination train encoders to be invariant to pre-defined transformations of the same instance. While most methods treat different views of the same image as posit…

Contrastive LearningFine-Grained Image ClassificationImage ClassificationSelf-Supervised Image Classification+3

SimCSE: Simple Contrastive Learning of Sentence Embeddings

2021-04-18 · EMNLP 2021 11 · Tianyu Gao, Xingcheng Yao, Danqi Chen

This paper presents SimCSE, a simple contrastive learning framework that greatly advances state-of-the-art sentence embeddings. We first describe an unsupervised approach, which takes an input sentence and predicts itsel…

Contrastive LearningData AugmentationLinear-Probe ClassificationNatural Language Inference+4

Unsupervised Voice-Face Representation Learning by Cross-Modal Prototype Contrast

2022-04-28 · Boqing Zhu, Kele Xu, Changjian Wang, Zheng Qin 외

We present an approach to learn voice-face representations from the talking face videos, without any identity labels. Previous works employ cross-modal instance discrimination tasks to establish the correlation of voice …

Contrastive LearningRepresentation Learning